Optimal weighted hybrid pattern for content based medical image retrieval using modified spider monkey optimization

摘要

The current approaches for image retrieval are more concentrating on numerous image features. Texture, shape, spatial information, and color are the fundamental features to deal with flexible image datasets. This paper aims to develop new Content-Based Image Retrieval System based on Optimal Weighted Hybrid Pattern. Two relevant patters like Local Vector Pattern and Local Derivative Pattern are intended to develop a novel Content-Based Image Retrieval system. The optimal weighted hybrid pattern is implemented to derive a new feature vector, so that the weight is optimized by a modified optimization algorithm called Improved Local Leader-based Spider Monkey Optimization to maximize the precision and recall of the retrieved images. The retrieval of the image is done by measuring the similarity based on Mean Square Distance between the features of query image as well as training image. Finally, the performance comparison of the proposed and the traditional patterns shows its reliable performance.